| Auteur | SHA1 Bericht | Datum |
|---|---|---|
|
|
7edf3d8df0 llm as a judge running now | 3 weken geleden |
|
|
57c05170eb added llm as a judge reward func | 4 weken geleden |
|
|
c88e10fab6 grpo llama 3.2 3b with 3 reward functions | 4 weken geleden |